© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99379
    Prev
    Next
    INDEX
    Explanations

    Republican Party

    np_acts-logits-general · gemini-2.5-flash-lite

    The main thing this neuron does is detect occurrences of the word “Republican,” i.e. references to the Republican Party.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )
    -3.27
     '
    -3.16
    on
    -2.83
     неболь
    -2.77
     You
    -2.69
    翃
    -2.61
     we
    -2.58
    </em>
    -2.48
     `
    -2.48
    食物
    -2.41
    POSITIVE LOGITS
    Ꭳ
    4.22
     parachoque
    3.83
    Ꮵ
    3.44
    缦
    3.38
    淠
    3.34
    蒹
    3.25
    屄
    3.22
    酲
    3.20
    𖡼
    3.19
    沇
    3.17
    Activations Density 0.004%

    No Known Activations